INDEX

Explanations

mentions of timelines and events as they relate to specific occurrences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓧ

-0.53

 الدولى

-0.52

hyrchwyd

-0.50

etro

-0.46

sbin

-0.45

كامل

-0.45

 exécu

-0.45

mappedBy

-0.44

FontOfSize

-0.44

 shutil

-0.44

POSITIVE LOGITS

 leading

1.60

 preceding

1.58

 lead

1.50

Leading

1.44

 Leading

1.40

leading

1.40

 prior

1.39

 previo

1.32

 preparation

1.28

 precede

1.28

Activations Density 0.314%

mentions of timelines and events as they relate to specific occurrences

No Comments

No Known Activations